linux/arch/riscv/kernel/process.c
Linus Torvalds 1ec6574a3c This set of changes updates init and user mode helper tasks to be
ordinary user mode tasks.
 
 In commit 40966e316f ("kthread: Ensure struct kthread is present for
 all kthreads") caused init and the user mode helper threads that call
 kernel_execve to have struct kthread allocated for them.  This struct
 kthread going away during execve in turned made a use after free of
 struct kthread possible.
 
 The commit 343f4c49f2 ("kthread: Don't allocate kthread_struct for
 init and umh") is enough to fix the use after free and is simple enough
 to be backportable.
 
 The rest of the changes pass struct kernel_clone_args to clean things
 up and cause the code to make sense.
 
 In making init and the user mode helpers tasks purely user mode tasks
 I ran into two complications.  The function task_tick_numa was
 detecting tasks without an mm by testing for the presence of
 PF_KTHREAD.  The initramfs code in populate_initrd_image was using
 flush_delayed_fput to ensuere the closing of all it's file descriptors
 was complete, and flush_delayed_fput does not work in a userspace thread.
 
 I have looked and looked and more complications and in my code review
 I have not found any, and neither has anyone else with the code sitting
 in linux-next.
 
 Link: https://lkml.kernel.org/r/87mtfu4up3.fsf@email.froward.int.ebiederm.org
 
 Eric W. Biederman (8):
       kthread: Don't allocate kthread_struct for init and umh
       fork: Pass struct kernel_clone_args into copy_thread
       fork: Explicity test for idle tasks in copy_thread
       fork: Generalize PF_IO_WORKER handling
       init: Deal with the init process being a user mode process
       fork: Explicitly set PF_KTHREAD
       fork: Stop allowing kthreads to call execve
       sched: Update task_tick_numa to ignore tasks without an mm
 
  arch/alpha/kernel/process.c      | 13 ++++++------
  arch/arc/kernel/process.c        | 13 ++++++------
  arch/arm/kernel/process.c        | 12 ++++++-----
  arch/arm64/kernel/process.c      | 12 ++++++-----
  arch/csky/kernel/process.c       | 15 ++++++-------
  arch/h8300/kernel/process.c      | 10 ++++-----
  arch/hexagon/kernel/process.c    | 12 ++++++-----
  arch/ia64/kernel/process.c       | 15 +++++++------
  arch/m68k/kernel/process.c       | 12 ++++++-----
  arch/microblaze/kernel/process.c | 12 ++++++-----
  arch/mips/kernel/process.c       | 13 ++++++------
  arch/nios2/kernel/process.c      | 12 ++++++-----
  arch/openrisc/kernel/process.c   | 12 ++++++-----
  arch/parisc/kernel/process.c     | 18 +++++++++-------
  arch/powerpc/kernel/process.c    | 15 +++++++------
  arch/riscv/kernel/process.c      | 12 ++++++-----
  arch/s390/kernel/process.c       | 12 ++++++-----
  arch/sh/kernel/process_32.c      | 12 ++++++-----
  arch/sparc/kernel/process_32.c   | 12 ++++++-----
  arch/sparc/kernel/process_64.c   | 12 ++++++-----
  arch/um/kernel/process.c         | 15 +++++++------
  arch/x86/include/asm/fpu/sched.h |  2 +-
  arch/x86/include/asm/switch_to.h |  8 +++----
  arch/x86/kernel/fpu/core.c       |  4 ++--
  arch/x86/kernel/process.c        | 18 +++++++++-------
  arch/xtensa/kernel/process.c     | 17 ++++++++-------
  fs/exec.c                        |  8 ++++---
  include/linux/sched/task.h       |  8 +++++--
  init/initramfs.c                 |  2 ++
  init/main.c                      |  2 +-
  kernel/fork.c                    | 46 +++++++++++++++++++++++++++++++++-------
  kernel/sched/fair.c              |  2 +-
  kernel/umh.c                     |  6 +++---
  33 files changed, 234 insertions(+), 160 deletions(-)
 
 Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEgjlraLDcwBA2B+6cC/v6Eiajj0AFAmKaR/MACgkQC/v6Eiaj
 j0Aayg/7Bx66872d9c6igkJ+MPCTuh+v9QKCGwiYEmiU4Q5sVAFB0HPJO27qC14u
 630X0RFNZTkPzNNEJNIW4kw6Dj8s8YRKf+FgQAVt4SzdRwT7eIPDjk1nGraopPJ3
 O04pjvuTmUyidyViRyFcf2ptx/pnkrwP8jUSc+bGTgfASAKAgAokqKE5ecjewbBc
 Y/EAkQ6QW7KxPjeSmpAHwI+t3BpBev9WEC4PbhRhsBCQFO2+PJiklvqdhVNBnIjv
 qUezll/1xv9UYgniB15Q4Nb722SmnWSU3r8as1eFPugzTHizKhufrrpyP+KMK1A0
 tdtEJNs5t2DZF7ZbGTFSPqJWmyTYLrghZdO+lOmnaSjHxK4Nda1d4NzbefJ0u+FE
 tutewowvHtBX6AFIbx+H3O+DOJM2IgNMf+ReQDU/TyNyVf3wBrTbsr9cLxypIJIp
 zze8npoLMlB7B4yxVo5ES5e63EXfi3iHl0L3/1EhoGwriRz1kWgVLUX/VZOUpscL
 RkJHsW6bT8sqxPWAA5kyWjEN+wNR2PxbXi8OE4arT0uJrEBMUgDCzydzOv5tJB00
 mSQdytxH9LVdsmxBKAOBp5X6WOLGA4yb1cZ6E/mEhlqXMpBDF1DaMfwbWqxSYi4q
 sp5zU3SBAW0qceiZSsWZXInfbjrcQXNV/DkDRDO9OmzEZP4m1j0=
 =x6fy
 -----END PGP SIGNATURE-----

Merge tag 'kthread-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull kthread updates from Eric Biederman:
 "This updates init and user mode helper tasks to be ordinary user mode
  tasks.

  Commit 40966e316f ("kthread: Ensure struct kthread is present for
  all kthreads") caused init and the user mode helper threads that call
  kernel_execve to have struct kthread allocated for them. This struct
  kthread going away during execve in turned made a use after free of
  struct kthread possible.

  Here, commit 343f4c49f2 ("kthread: Don't allocate kthread_struct for
  init and umh") is enough to fix the use after free and is simple
  enough to be backportable.

  The rest of the changes pass struct kernel_clone_args to clean things
  up and cause the code to make sense.

  In making init and the user mode helpers tasks purely user mode tasks
  I ran into two complications. The function task_tick_numa was
  detecting tasks without an mm by testing for the presence of
  PF_KTHREAD. The initramfs code in populate_initrd_image was using
  flush_delayed_fput to ensuere the closing of all it's file descriptors
  was complete, and flush_delayed_fput does not work in a userspace
  thread.

  I have looked and looked and more complications and in my code review
  I have not found any, and neither has anyone else with the code
  sitting in linux-next"

* tag 'kthread-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  sched: Update task_tick_numa to ignore tasks without an mm
  fork: Stop allowing kthreads to call execve
  fork: Explicitly set PF_KTHREAD
  init: Deal with the init process being a user mode process
  fork: Generalize PF_IO_WORKER handling
  fork: Explicity test for idle tasks in copy_thread
  fork: Pass struct kernel_clone_args into copy_thread
  kthread: Don't allocate kthread_struct for init and umh
2022-06-03 16:03:05 -07:00

190 lines
5.0 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
* Chen Liqin <liqin.chen@sunplusct.com>
* Lennox Wu <lennox.wu@sunplusct.com>
* Copyright (C) 2012 Regents of the University of California
* Copyright (C) 2017 SiFive
*/
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/tick.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/csr.h>
#include <asm/stacktrace.h>
#include <asm/string.h>
#include <asm/switch_to.h>
#include <asm/thread_info.h>
#include <asm/cpuidle.h>
register unsigned long gp_in_global __asm__("gp");
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
extern asmlinkage void ret_from_fork(void);
extern asmlinkage void ret_from_kernel_thread(void);
void arch_cpu_idle(void)
{
cpu_do_idle();
raw_local_irq_enable();
}
void __show_regs(struct pt_regs *regs)
{
show_regs_print_info(KERN_DEFAULT);
if (!user_mode(regs)) {
pr_cont("epc : %pS\n", (void *)regs->epc);
pr_cont(" ra : %pS\n", (void *)regs->ra);
}
pr_cont("epc : " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n",
regs->epc, regs->ra, regs->sp);
pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n",
regs->gp, regs->tp, regs->t0);
pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n",
regs->t1, regs->t2, regs->s0);
pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n",
regs->s1, regs->a0, regs->a1);
pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n",
regs->a2, regs->a3, regs->a4);
pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n",
regs->a5, regs->a6, regs->a7);
pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n",
regs->s2, regs->s3, regs->s4);
pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n",
regs->s5, regs->s6, regs->s7);
pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n",
regs->s8, regs->s9, regs->s10);
pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n",
regs->s11, regs->t3, regs->t4);
pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT "\n",
regs->t5, regs->t6);
pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n",
regs->status, regs->badaddr, regs->cause);
}
void show_regs(struct pt_regs *regs)
{
__show_regs(regs);
if (!user_mode(regs))
dump_backtrace(regs, NULL, KERN_DEFAULT);
}
#ifdef CONFIG_COMPAT
static bool compat_mode_supported __read_mostly;
bool compat_elf_check_arch(Elf32_Ehdr *hdr)
{
return compat_mode_supported &&
hdr->e_machine == EM_RISCV &&
hdr->e_ident[EI_CLASS] == ELFCLASS32;
}
static int __init compat_mode_detect(void)
{
unsigned long tmp = csr_read(CSR_STATUS);
csr_write(CSR_STATUS, (tmp & ~SR_UXL) | SR_UXL_32);
compat_mode_supported =
(csr_read(CSR_STATUS) & SR_UXL) == SR_UXL_32;
csr_write(CSR_STATUS, tmp);
pr_info("riscv: ELF compat mode %s",
compat_mode_supported ? "supported" : "failed");
return 0;
}
early_initcall(compat_mode_detect);
#endif
void start_thread(struct pt_regs *regs, unsigned long pc,
unsigned long sp)
{
regs->status = SR_PIE;
if (has_fpu()) {
regs->status |= SR_FS_INITIAL;
/*
* Restore the initial value to the FP register
* before starting the user program.
*/
fstate_restore(current, regs);
}
regs->epc = pc;
regs->sp = sp;
#ifdef CONFIG_64BIT
regs->status &= ~SR_UXL;
if (is_compat_task())
regs->status |= SR_UXL_32;
else
regs->status |= SR_UXL_64;
#endif
}
void flush_thread(void)
{
#ifdef CONFIG_FPU
/*
* Reset FPU state and context
* frm: round to nearest, ties to even (IEEE default)
* fflags: accrued exceptions cleared
*/
fstate_off(current, task_pt_regs(current));
memset(&current->thread.fstate, 0, sizeof(current->thread.fstate));
#endif
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
fstate_save(src, task_pt_regs(src));
*dst = *src;
return 0;
}
int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
{
unsigned long clone_flags = args->flags;
unsigned long usp = args->stack;
unsigned long tls = args->tls;
struct pt_regs *childregs = task_pt_regs(p);
/* p->thread holds context to be restored by __switch_to() */
if (unlikely(args->fn)) {
/* Kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
childregs->gp = gp_in_global;
/* Supervisor/Machine, irqs on: */
childregs->status = SR_PP | SR_PIE;
p->thread.ra = (unsigned long)ret_from_kernel_thread;
p->thread.s[0] = (unsigned long)args->fn;
p->thread.s[1] = (unsigned long)args->fn_arg;
} else {
*childregs = *(current_pt_regs());
if (usp) /* User fork */
childregs->sp = usp;
if (clone_flags & CLONE_SETTLS)
childregs->tp = tls;
childregs->a0 = 0; /* Return value of fork() */
p->thread.ra = (unsigned long)ret_from_fork;
}
p->thread.sp = (unsigned long)childregs; /* kernel sp */
return 0;
}